Edge AI & TinyML: your first working example

Why this example matters

A simple flash-memory calculation checks whether model weights and metadata fit the device capacity. The remaining bytes show that size budgeting is a concrete engineering constraint.

What you will be able to do

• Recognize the input values and describe what they represent in Edge AI & TinyML.
• Run the Edge AI & TinyML program and explain why its displayed output follows from the recorded operations.
• Identify a limitation of the Edge AI & TinyML activity before applying similar reasoning to a real system.

Original worked program

The following Edge AI & TinyML demonstration uses small invented values so you can trace every operation. The Edge AI & TinyML activity uses only Python standard-library features; it downloads no model and calls no paid service.

flash_budget_bytes = 2048
weights = 800
metadata = 300
used = weights + metadata
print("Fits flash:", used <= flash_budget_bytes)
print("Remaining bytes:", flash_budget_bytes - used)

Actual output from Python

Fits flash: True
Remaining bytes: 948

Read each instruction

1. flash_budget_bytes = 2048The assignment gives a name to a value or a calculated result in Edge AI & TinyML. In the Edge AI & TinyML activity, check the named values on that line rather than memorizing symbols.
2. weights = 800The assignment gives a name to a value or a calculated result in Edge AI & TinyML. In the Edge AI & TinyML activity, check the named values on that line rather than memorizing symbols.
3. metadata = 300The assignment gives a name to a value or a calculated result in Edge AI & TinyML. In the Edge AI & TinyML activity, check the named values on that line rather than memorizing symbols.
4. used = weights + metadataThe assignment gives a name to a value or a calculated result in Edge AI & TinyML. In the Edge AI & TinyML activity, check the named values on that line rather than memorizing symbols.

Observe the results

To verify the Edge AI & TinyML result, copy the program into a fresh file and run it once without modification. Then change only one input. For the Edge AI & TinyML trial, record what you predict before pressing Run again. Compare the Edge AI & TinyML prediction with the observed result.

Second original practice: Memory and flash constraints

The Edge AI & TinyML extension changes the task, not just the numbers in the first example. Study its new data structure or operation, then decide how the result supports the milestone “Memory and flash constraints”.

raw_weights = [0.1, 0.7, -0.4]
scale = 10
packed = [round(w*scale) for w in raw_weights]
print("Toy integer weights:", packed)

Actual second output

Toy integer weights: [1, 7, -4]

For the Edge AI & TinyML extension, read the code from its first assignment or import to its final print statement. Explain the additional Edge AI & TinyML idea introduced by this extension, then design a check that could reveal a mistake. The Edge AI & TinyML extension output above was recorded by running that independent program.

What the example does not prove

A model that fits memory may still be too slow or power-hungry. Real deployments must measure inference latency, RAM usage, update safety and sensor reliability.

A reliable Edge AI & TinyML project also needs an explicit objective, test cases that were not used to tune the approach, documentation of the assumptions, and review of situations where the result might mislead the user. Do not mistake the small Edge AI & TinyML program for evidence of accuracy or safety in a deployed application.

How to validate your own result

For Edge AI & TinyML, a convincing result starts with a written claim about the actual task, not the appearance of a successful print statement. For Edge AI & TinyML, list the initial values and the one value you will vary; record a prediction that could be disproved. Save both Edge AI & TinyML outputs as separate records to avoid mixing up the results of the two investigations. A correct Python run only establishes that the particular instructions executed; it does not establish that the assumptions match every situation in which Edge AI & TinyML might be used.

Connect this trial to “Sensor input streams” without claiming that the milestone is already complete. Name a measurement you would collect for Edge AI & TinyML, a plausible error source and a person able to review the decision. The later topic “Sampling decisions” deserves its own investigation with different evidence. Keeping these questions separate prevents your Edge AI & TinyML learning journal from becoming a collection of exercises that all make the same claim.

Finally, keep the Edge AI & TinyML experiment reproducible: include the Python version, exact script, input values, observed results and any unexpected behavior. If a Edge AI & TinyML investigation uses external data, document the source and your permission to use those records. A new learner should be able to explain every output line in ordinary words before moving into the next milestone of Edge AI & TinyML.

Second verified lab: Graph in practice

To deepen Chapter 1 of Edge AI & TinyML, compare the first calculation with a different, executable experiment. The small graph lab below illustrates a related technique, not every possible implementation of microcontroller versus server.

# Course: Edge AI & TinyML | Chapter 1 | Subject: Microcontroller versus server
# A shortest-path search through an unweighted graph
from collections import deque
adj={"A":["B","C"],"B":["D"],"C":["D","E"],"D":["F"],"E":["F"],"F":[]}
queue=deque([("A",["A"])])
seen={"A"}
while queue:
    node,path=queue.popleft()
    if node=="F":
        print("Shortest path:", " -> ".join(path))
        print("Edge count:",len(path)-1)
        break
    for neighbor in adj[node]:
        if neighbor not in seen:
            seen.add(neighbor);queue.append((neighbor,path+[neighbor]))

Actual output of the displayed code

Shortest path: A -> B -> D -> F
Edge count: 3

While examining your first working example in the edge ai and tinyml course (chapter 1), apply this test: Breadth-first search expands by distance in edges, so the first found path to the target is shortest in an unweighted graph. For the transit delay observations exercise, distinguish what the code observes from any stronger predictive or causal claim.

While examining your first working example in the edge ai and tinyml course (chapter 1), apply this test: Interpretation limit. Weighted or negative-cost edges require a different shortest-path method and assumptions. Record the changed inputs and compare both outputs before extending the result to a project.Interpretation limit. Weighted or negative-cost edges require a different shortest-path method and assumptions. Record the changed inputs and compare both outputs before extending the result to a project.

20 practice questions and worked answers

Test your understanding of your first working example in the edge ai and tinyml course (chapter 1). Compare the claims in both runnable labs, and use the outputs to defend each numerical response.

Build one original mini-project

Chapter 1 checkpoint: Explain how microcontroller versus server affects the transit delay observations example; demonstrate one failing input; then propose a revision with an acceptance test and a recorded output. This checkpoint belongs to the Edge AI & TinyML course.

Create a device budget with separate entries for code, model, sensor buffers and logging, then check what cannot fit.

A six-step practice plan

1. Microcontroller versus server. For the “Microcontroller versus server” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.
2. Memory and flash constraints. For the “Memory and flash constraints” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.
3. Sensor input streams. For the “Sensor input streams” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.
4. Sampling decisions. For the “Sampling decisions” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.
5. Fixed-point arithmetic. For the “Fixed-point arithmetic” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.
6. Tiny feature extraction. For the “Tiny feature extraction” exercise, identify one observable result and record what would demonstrate progress in Edge AI & TinyML.

Save your original inputs, your changed inputs, the two actual outputs and a short explanation of what you learned about Edge AI & TinyML. The Edge AI & TinyML record forms evidence for the first milestone of your project portfolio.

Where you go next

Your Edge AI & TinyML roadmap has 18 subject-specific milestones progressing toward evaluation and a capstone. Future Edge AI & TinyML lessons will require new demonstrations and evidence, beyond the skills taught in this first chapter.